Linear Neural Network Training Algorithms For Real-World Benchmark Problems

References

• Amari , S. , Murata , N. , Muller , K. R. , Finke , M. and Yang , H. 1995 . Asymptotic statistical theory of overtraining and cross-validation, METR 95-06; Department of Mathematical Engineering and Information Physics , University of Tokyo . Hongo 7-3-1, Bunkyo-ku, Tokyo 113, Japan
   Google Scholar
• Goulianas , K. , Adamopoulos , M and Margaritis , K. G. 1997 . Structured artificial neural networks for last batch LMS algorithms . Neural, Parallel and Scientific Computations , 5 (4} ) : 549 – 562 .
   Google Scholar
• Golub , G. H. and Van Loan , C. F. 1983 . Matrix Computations , Baltimore , MD : The Johns Hopkins University Press .
   Google Scholar
• Hassoun , M. H. 1995 . Fundamentals of Artificial Neural Networks , Cambridge , MA : The MIT Press .
   Google Scholar
• Zhi-Quan , Luo . 1991 . On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks . Neural Computation , 3 : 226 – 245 .
   Web of Science ®Google Scholar
• Margaritis , K. G. , Adamopoulos , M. , Goulianas , K. and Evans , D. J. 1994 . Artificial neural networks and iterative linear algebra methods . Parallel Algorithms and Applications , 3 : 31 – 44 .
   Google Scholar
• Polycarpou , M. and Ioannou , P. 1992 . Learning and convergence analysis of neural-type structured networks . IEEE Transactions on Neural Networks , 3 (1} ) : 39 – 50 .
   PubMedGoogle Scholar
• Lutz , Prechelt . 1994 . Proben1 - A Set of Neural Network Benchmark Problems and Benchmarking Rules , Vol. 21 , 94 Technical Report : Universitat Karlsruhe .
   Google Scholar
• Riedmiller , M. and Braun , H. A direct adaptive method for fester backpropagation learning: the RPROP algorithm . Proceedings of the IEEE International Conference on Neural Networks . April 1993 , San Fransisco , CA . IEEE .
   Google Scholar
• Rumelhart , D. E. , Hinton , G. E. and Williams , R. J. 1986 . “ Learning internal representation by error propagation ” . In Parallel Distributed Processing I , Edited by: Rumelhart , D. E. and McClelland , J. Cambridge , MA : MIT Press .
   Google Scholar
• Rumelhart , D. E. and McClelland , J. 1986 . Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Cambridge , MA : MIT Press .
   Google Scholar
• Sarle , W. S. Stopped training and other remedies for overfitting . Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics . pp. 352 – 360 .
   Google Scholar
• Stuart , G. , Bienenstock , E. and Doursat , R. 1992 . Neural networks and the bias/variance dilemma . Neural Computation , 4 : 1 – 58 .
   Web of Science ®Google Scholar
• Wang , L. X. and Mendel , J. M . 1991 . Three-dimensional structured networks for matrix equation solving . IEEE Transactions on Computers , 40 (12} ) : 1337 – 1346 .
   Web of Science ®Google Scholar
• Wang , L. X. and Mendel , J. M. 1992 . Parallel structured networks for solving a wide variety of matrix algebra problems . Journal of Parallel and Distributed Computing , 14 : 236 – 247 .
   Web of Science ®Google Scholar
• Wang , C. , Venkatesh , S. S. and Judd , J. S. 1994 . Optimal stopping and effective machine complexity in learning . NIPS6 , : 303 – 310 .
   Google Scholar
• Widrow , B. and Hoff , M. E. Jr. 1960 . Adaptive switching circuits . IRE Western Electric Show and Convention Record, Part , 4 : 96 – 104 .
   Google Scholar
• Widrow , B. and Lehr , M. 1990 . 30 years of adaptive neural networks: perception, madaline and backpropagation . Proceedings of the IEEE , 78 (9} ) : 1415 – 1442 .
   Web of Science ®Google Scholar